Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1876 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1796983 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1216911 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1714731 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5660. Min Act: -0.0000

Data Index: 7497 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5009. Min Act: -0.0000

Data Index: 15566 (The Pile)

Max Activating Token Index: 604

Text #5

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1024905 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1043955 (The Pile)

Max Activating Token Index: 280

Text #7

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1150894 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1675833 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1893440 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5120. Min Act: -0.0000

Data Index: 854493 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1511630 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1739727 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1155662 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4905. Min Act: -0.0000

Data Index: 388885 (The Pile)

Max Activating Token Index: 277

Text #15

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1205208 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1869199 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4686. Min Act: -0.0000

Data Index: 443565 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4413. Min Act: -0.0000

Data Index: 225393 (The Pile)

Max Activating Token Index: 324

Text #19

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1999095 (The Pile)

Max Activating Token Index: 336